Python探索之pLSA实现代码

# -*- coding: utf-8 -*-import mathimport randomimport jiebaimport codecsimport datetimeclass pLSA_lph():  def __init__(self, ntopic = 5):    self.n_doc = 0    self.n_word = 0    self.n_topic = ntopic    self.corpus = None    self.p_z_dw = None    self.p_w_z = None    self.p_z_d = None    self.likelihood = 0    self.vocab = None    self.stop_words = [u'，', u'。', u'、', u'（', u'）', u'·', u'！', u' ', u'：', u'“', u'”', u'/n']  # 每行和为1的正实数，概率分布;  def _rand_mat(self, sizex, sizey):    ret = []    for i in xrange(sizex):      ret.append([])      for _ in xrange(sizey):        ret[-1].append(random.random())      norm = sum(ret[-1])      for j in xrange(sizey):        ret[-1][j] /= norm    return ret  #从文本中计算词频稀疏矩阵，这里存储模型仿照LDA  def loadCorpus(self, fn):    # 中文分词    f = open(fn, 'r')    text = f.readlines()    text = r' '.join(text)    seg_generator = jieba.cut(text)    seg_list = [i for i in seg_generator if i not in self.stop_words]    seg_list = r' '.join(seg_list)    # 切割统计所有出现的词纳入词典    seglist = seg_list.split(" ")    self.vocab = []    for word in seglist:      if (word != u' ' and word not in self.vocab):        self.vocab.append(word)    self.n_word =len(self.vocab)    CountMatrix = []    f.seek(0, 0)    # 统计每个文档中出现的词频    for line in f:      # 置零      count = [0 for i in range(len(self.vocab))]      text = line.strip()      # 但还是要先分词      seg_generator = jieba.cut(text)      seg_list = [i for i in seg_generator if i not in self.stop_words]      seg_list = r' '.join(seg_list)      seglist = seg_list.split(" ")      # 查询词典中的词出现的词频      for word in seglist:        if word in self.vocab:          count[self.vocab.index(word)] += 1      CountMatrix.append(count)    f.close()    self.corpus = CountMatrix    self.n_doc = len(CountMatrix)    #初始化    self.p_z_d = self._rand_mat(self.n_topic, self.n_doc)    self.p_w_z = self._rand_mat(self.n_word, self.n_topic)    self.p_z_dw =[]    for k in range(self.n_topic):      self.p_z_dw.append(self._rand_mat(self.n_doc, self.n_word))  def _e_step(self):    for k in range(self.n_topic):      for d in range(self.n_doc):        for j in range(self.n_word):          _d_wz_zd = 0          for kk in range(self.n_topic):            _d_wz_zd += self.p_w_z[j][kk]*self.p_z_d[kk][d]          if _d_wz_zd <= 0:            _d_wz_zd = 1e-6          self.p_z_dw[k][d][j] = self.p_w_z[j][k]*self.p_z_d[k][d]/_d_wz_zd  def _m_step(self):    print "updating Pn(Wj|Zk).../r"    for j in range(self.n_word):      for k in range(self.n_topic):        _d_dw_zdw = 0        for d in range(self.n_doc):          _d_dw_zdw += self.corpus[d][j]*self.p_z_dw[k][d][j]        _d_dw_zdw_sum = 0        for jj in range(self.n_word):          _d_dw_zdw_i = 0          for d in range(self.n_doc):            _d_dw_zdw_i += self.corpus[d][jj]*self.p_z_dw[k][d][jj]          _d_dw_zdw_sum += _d_dw_zdw_i        if _d_dw_zdw_sum <= 0:          _d_dw_zdw_sum = 1e-6        self.p_w_z[j][k] = _d_dw_zdw/_d_dw_zdw_sum    print "updating Pn(Zk|Di).../r"    for k in range(self.n_topic):      for d in range(self.n_doc):        _d_dw_zdw = 0        for j in range(self.n_word):          _d_dw_zdw += self.corpus[d][j]*self.p_z_dw[k][d][j]        _d_dw_zdw_sum = 0        for kk in range(self.n_topic):          _d_dw_zdw_i = 0          for j in range(self.n_word):            _d_dw_zdw_i += self.corpus[d][j]*self.p_z_dw[kk][d][j]          _d_dw_zdw_sum += _d_dw_zdw_i        if _d_dw_zdw_sum <= 0:          _d_dw_zdw_sum = 1e-6        self.p_z_d[k][d] = _d_dw_zdw/_d_dw_zdw_sum  #计算最大似然值  def _cal_max_likelihood(self):    self.likelihood = 0    for d in range(self.n_doc):      for j in range(self.n_word):        _dP_wjdi = 0        for k in range(self.n_topic):          _dP_wjdi += self.p_w_z[j][k]*self.p_z_d[k][d]        _dP_wjdi = 1.0/self.n_doc*_dP_wjdi        self.likelihood += self.corpus[d][j]*math.log(_dP_wjdi)  #迭代训练  def train(self, n_iter = 100, d_delta = 1e-6,log_fn = "log.log"):    itr = 0    delta =10e9    _likelihood = 0    f = open(log_fn, 'w')    while itr < n_iter and delta > d_delta:      _likelihood = self.likelihood      self._e_step()      self._m_step()      self._cal_max_likelihood()      itr += 1      delta = abs(self.likelihood - _likelihood)      t1 = datetime.datetime.now().strftime('%Y-%m-%d-%y %H:%M:%S');      f.write("%s iteration %d, max-likelihood = %.6f/n"%(t1, itr, self.likelihood))      print "%s iteration %d, max-likelihood = %.6f"%(t1, itr, self.likelihood)    f.close()  def printVocabulary(self):    print "vocabulary:"    for word in self.vocab:      print word,    print  def saveVocabulary(self, fn):    f = codecs.open(fn, 'w', 'utf-8')    for word in self.vocab:      f.write("%s/n"%word)    f.close()  def printWordOfTopic(self):    for k in range(self.n_topic):      print "Topic %d"%k,      for j in range(self.n_word):        print self.p_w_z[j][k],      print  def saveWordOfTopic(self,fn):    f = open(fn, 'w')    for j in range(self.n_word):      f.write(", w%d"%j)    f.write("/n")    for k in range(self.n_topic):      f.write("topic %d"%k)      for j in range(self.n_word):        f.write(", %.6f"%self.p_w_z[j][k])      f.write("/n")    f.close()  def printTopicOfDoc(self):    for d in range(self.n_doc):      print "Doc %d"%d,      for k in range(self.n_topic):        print self.p_z_d[k][d],      print  def saveTopicOfDoc(self, fn):    f = open(fn, 'w')    for k in range(self.n_topic):      f.write(", z%d" % k)    f.write("/n")    for d in range(self.n_doc):      f.write("doc %d" % d)      for k in range(self.n_topic):        f.write(", %.6f" % self.p_z_d[k][d])      f.write("/n")    f.close()

<span style="font-family: Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255);">新华社北京11月26日电中共中央总书记、国家主席习近平26日向古巴共产党中央委员会第一书记、国务委员会主席兼部长会议主席劳尔·卡斯特罗致唁电，代表中国党、政府、人民并以个人名义，对菲德尔·卡斯特罗同志逝世表示最沉痛的哀悼，向其家属致以最诚挚的慰问。全文如下：惊悉古巴革命领导人菲德尔·卡斯特罗同志不幸逝世，我谨代表中国共产党、政府、人民，并以我个人的名义，向你并通过你向古巴共产党、政府、人民，对菲德尔·卡斯特罗同志的逝世表示最沉痛的哀悼，向其家属致以最诚挚的慰问。菲德尔·卡斯特罗同志是古巴共产党和古巴社会主义事业的缔造者，是古巴人民的伟大领袖。他把毕生精力献给了古巴人民争取民族解放、维护国家主权、建设社会主义的壮丽事业，为古巴人民建立了不朽的历史功勋，也为世界社会主义发展建立了不朽的历史功勋。菲德尔·卡斯特罗同志是我们这个时代的伟大人物，历史和人民将记住他。我多次同菲德尔·卡斯特罗同志见面，促膝畅谈，他的真知灼见令我深受启发，他的音容笑貌犹在眼前。我深深怀念他，中国人民深深怀念他。菲德尔·卡斯特罗同志生前致力于中古友好，密切关注和高度评价中国发展进程，在他亲自关心和支持下，古巴成为第一个同新中国建交的拉美国家。建交56年来，中古关系长足发展，各领域务实合作成果丰硕，两国人民友谊与日俱增，这都与菲德尔·卡斯特罗同志的关怀和心血密不可分。菲德尔·卡斯特罗同志的逝世是古巴和拉美人民的重大损失，不仅使古巴和拉美人民失去了一位优秀儿子，也使中国人民失去了一位亲密的同志和真诚的朋友。他的光辉形象和伟大业绩将永载史册。我相信，在主席同志坚强领导下，古巴党、政府、人民必将继承菲德尔·卡斯特罗同志的遗志，化悲痛为力量，在社会主义建设事业中不断取得新的成绩。中古两党、两国、两国人民友谊必将得到巩固和发展。伟大的菲德尔·卡斯特罗同志永垂不朽！（完）</span> 

if __name__=="__main__":  _plsa = pLSA_lph(2)  _plsa.loadCorpus(u"C://Users/Administrator/Desktop//zhongwen.txt")  _plsa.train()  _plsa.printTopicOfDoc()  _plsa.printWordOfTopic()  _plsa.saveTopicOfDoc(u"C://Users/Administrator/Desktop//topic_doc.txt")  _plsa.saveWordOfTopic(u"C://Users/Administrator/Desktop//word_topic.txt")